INDEX
Explanations
languages being spoken or mentioned
mentions of different languages
New Auto-Interp
Negative Logits
urion
-0.91
onnaissance
-0.90
ndra
-0.86
inson
-0.83
vre
-0.81
alions
-0.77
xus
-0.77
responsible
-0.76
llan
-0.76
igham
-0.75
POSITIVE LOGITS
translation
1.11
diction
1.04
language
1.03
subtitles
1.00
pronunciation
0.94
languages
0.93
dialect
0.90
translations
0.90
translator
0.88
accents
0.88
Activations Density 0.080%